blog
blog copied to clipboard
huggingface
Public repo for HF blog posts
https://huggingface.co/blog/llama31#inference-memory-requirements Please tell me about the calculation of inference memory requirements for Llama 3.1 in this post. The table below shows an excerpt of the KV cache size for FP16....
Hi, thanks to the authors for this amazing work! I would really appreciate if you can provide any help on the error I encountered. I was following the trainer part...
[This space](https://huggingface.co/spaces/coreml-projects/transformers-to-coreml) that is linked/embedded in the blog post [Releasing Swift Transformers: Run On-Device LLMs in Apple Devices](https://huggingface.co/blog/swift-coreml-llm) is not functional.
 I have faced this problem when try to finetune WAV2VEC2 but I cannot solve it
cc @AK391 could be a good idea! RSS feed for hf.co/papers _Originally posted by @julien-c in https://github.com/huggingface/blog/issues/42#issuecomment-1658369564_ As already proposed in issue #42, it would be great to have an...
When trying to use in Ollama reference : https://github.com/ollama/ollama/issues/5731
The llama 3.1 tool calling template says "orginal user question" instead of the "original user question". Unless it's the actual prompt pattern the model is trained with, this should affect...
